--- title: Introducing Harness Agent DLC: New Capabilities for the... description: Harness has launched Agent DLC, a set of five new products and capabilities designed to extend its software delivery platform to cover the full AI Agent... canonical: https://daily.dev/posts/introducing-harness-agent-dlc-new-capabilities-for-the-ai-agent-development-lifecycle-hwl8nubmc twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Introducing Harness Agent DLC: New Capabilities for the AI Agent Development Lifecycle | daily.dev og:description: Harness has launched Agent DLC, a set of five new products and capabilities designed to extend its software delivery platform to cover the full AI Agent... og:url: https://daily.dev/posts/introducing-harness-agent-dlc-new-capabilities-for-the-ai-agent-development-lifecycle-hwl8nubmc og:image: https://api.daily.dev/og/posts/HWl8NubmC.png og:image:alt: Introducing Harness Agent DLC: New Capabilities for the AI Agent Development Lifecycle og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Introducing Harness Agent DLC: New Capabilities for the AI Agent Development Lifecycle **[SD Times](https://daily.dev/sources/sdtimes)** · 6 min read · 1 upvotes · 0 comments ## Summary Harness has launched Agent DLC, a set of five new products and capabilities designed to extend its software delivery platform to cover the full AI Agent Development Lifecycle. The launch addresses the challenge that AI agents are non-deterministic, making traditional CI/CD testing and deployment practices insufficient. Key new capabilities include Harness AI Evals for measurable agent quality gates, Agent Deployments supporting Amazon Bedrock AgentCore and Google Agent Runtime, AI Configs for runtime prompt and model management via feature flags, AI Asset Catalog for organization-wide agent discovery, and AgentTrace for session-level observability. Security features span shift-left tools (Primitive Scanning, AIBOM, adversarial AI testing against OWASP Top 10 LLM risks) and shield-right controls (AI Firewall, Agent Discovery and Posture Management). Harness is also open-sourcing foundational tracing components harness-sdk and harness-evals. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How does Harness AI Evals test AI agents for regressions? Harness AI Evals lets teams define evaluation datasets, configure scoring functions, and set quality gates that automatically detect regressions whenever an agent or its underlying model changes. It specifically addresses the non-deterministic nature of LLM-based agents, where identical inputs can produce different outputs across separate runs. _daily.dev surfaces platform updates like this for teams evaluating how to test non-deterministic AI agents._ ### Can Harness deploy AI agents to Amazon Bedrock AgentCore and Google Agent Runtime? Yes, Harness Agent Deployments extends its existing canary releases, approval workflows, and OPA policy guardrails to managed agent runtimes including Amazon Bedrock AgentCore and Google's Agent Runtime. This lets agents ship through existing Harness pipelines instead of separate cloud-provider-specific deployment workflows. _Engineers comparing agent deployment options across cloud runtimes can track platform news like this on daily.dev._ ### What security measures protect AI agents from prompt injection attacks? Harness combines shift-left and shield-right security capabilities for agents: Primitive Scanning flags misconfigurations in skills, prompts, and models; AIBOM tracks every model, tool, and dependency; AI Testing runs agents against OWASP Top 10 LLM and Agentic AI risks; and an AI Firewall enforces real-time policy against prompt injection, tool misuse, and data exfiltration. _daily.dev helps engineers securing agentic systems keep up with new defenses against prompt injection and tool misuse._ ## Similar posts on daily.dev - [Harness Launches Autonomous Worker Agents for Software Delivery](https://daily.dev/posts/harness-launches-autonomous-worker-agents-for-software-delivery-gb2ydwalv) · SD Times · 3 upvotes · 0 comments - [“The harness is where the hard work is”: Harness bets on agents that enterprises can trust in production](https://daily.dev/posts/the-harness-is-where-the-hard-work-is-harness-bets-on-agents-that-enterprises-can-trust-in-produc-n15bmi6wz) · The New Stack · 0 upvotes · 0 comments - [Harness Extends AI Security Reach Now Spans Entire DevOps Workflow](https://daily.dev/posts/harness-extends-ai-security-reach-now-spans-entire-devops-workflow-dndldkpbf) · DevOps.com · 0 upvotes · 0 comments --- Tags: [#security](https://daily.dev/tags/security), [#ai-agents](https://daily.dev/tags/ai-agents), [#cicd](https://daily.dev/tags/cicd) [View this post on daily.dev](https://daily.dev/posts/introducing-harness-agent-dlc-new-capabilities-for-the-ai-agent-development-lifecycle-hwl8nubmc) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Introducing Harness Agent DLC: New Capabilities for the AI Agent Development Lifecycle","url":"https://daily.dev/posts/introducing-harness-agent-dlc-new-capabilities-for-the-ai-agent-development-lifecycle-hwl8nubmc","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/introducing-harness-agent-dlc-new-capabilities-for-the-ai-agent-development-lifecycle-hwl8nubmc"},"datePublished":"2026-07-21T20:43:24.159Z","dateModified":"2026-09-13T20:42:22.779Z","description":"Harness has launched Agent DLC, a set of five new products and capabilities designed to extend its software delivery platform to cover the full AI Agent...","image":"https://media.daily.dev/image/upload/s--P4t4XyoV--/f_auto/v1722860399/public/Placeholder%2001","thumbnailUrl":"https://media.daily.dev/image/upload/s--P4t4XyoV--/f_auto/v1722860399/public/Placeholder%2001","isAccessibleForFree":true,"articleSection":"SD Times","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"SD Times","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/d803c981e67b4edf928840534e1e1382","url":"https://daily.dev/sources/sdtimes"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/introducing-harness-agent-dlc-new-capabilities-for-the-ai-agent-development-lifecycle-hwl8nubmc","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"security,ai-agents,cicd","timeRequired":"PT6M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"SD Times","item":"https://daily.dev/sources/sdtimes"},{"@type":"ListItem","position":3,"name":"Introducing Harness Agent DLC: New Capabilities for the AI Agent Development Lifecycle"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/introducing-harness-agent-dlc-new-capabilities-for-the-ai-agent-development-lifecycle-hwl8nubmc#faq","mainEntity":[{"@type":"Question","name":"How does Harness AI Evals test AI agents for regressions?","acceptedAnswer":{"@type":"Answer","text":"Harness AI Evals lets teams define evaluation datasets, configure scoring functions, and set quality gates that automatically detect regressions whenever an agent or its underlying model changes. It specifically addresses the non-deterministic nature of LLM-based agents, where identical inputs can produce different outputs across separate runs. daily.dev surfaces platform updates like this for teams evaluating how to test non-deterministic AI agents."}},{"@type":"Question","name":"Can Harness deploy AI agents to Amazon Bedrock AgentCore and Google Agent Runtime?","acceptedAnswer":{"@type":"Answer","text":"Yes, Harness Agent Deployments extends its existing canary releases, approval workflows, and OPA policy guardrails to managed agent runtimes including Amazon Bedrock AgentCore and Google's Agent Runtime. This lets agents ship through existing Harness pipelines instead of separate cloud-provider-specific deployment workflows. Engineers comparing agent deployment options across cloud runtimes can track platform news like this on daily.dev."}},{"@type":"Question","name":"What security measures protect AI agents from prompt injection attacks?","acceptedAnswer":{"@type":"Answer","text":"Harness combines shift-left and shield-right security capabilities for agents: Primitive Scanning flags misconfigurations in skills, prompts, and models; AIBOM tracks every model, tool, and dependency; AI Testing runs agents against OWASP Top 10 LLM and Agentic AI risks; and an AI Firewall enforces real-time policy against prompt injection, tool misuse, and data exfiltration. daily.dev helps engineers securing agentic systems keep up with new defenses against prompt injection and tool misuse."}}]} ```